Studying Sensitivities of an EJB Performance Model

  • Authors:
  • C. M. Lladó;J. Lüthi;P. G. Harrison

  • Affiliations:
  • -;-;-

  • Venue:
  • MASCOTS '02 Proceedings of the 10th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

Often, at the time when a performance model is built,some of its input parameters are not known exactly. Thiscan be for a variety of reasons, such as the system itselfnot having been completed, a benchmarking process notyet having been carried out, or that precise estimates forthe parameters are very difficult to obtain. In these situations,interval values can be used to express the uncertaintiesof the input parameters and sensitivity studies ofperformance models have the potential to show the influenceof input parameter uncertainties on the resulting performancemeasures. In this paper we study the sensitivitiesof an Enterprise JavaBeans performance model. Thismodel is built using the standard method of model decompositionwhich gives various submodels. Solutions obtainedfor these submodels have been adapted to interval parametersand hence interval-based sensitivities are studied inthe so-called container submodel and then the whole model.Using these techniques, parameters that require to be characterisedmore carefully than others can be identified.